Modeling Relation Paths for Representation Learning of Knowledge Bases (2015-06-01T00:00:00.000000Z)

TL;DR

This model considers relation paths as translations between entities for representation learning, and addresses two key challenges: (1) Since not all relation paths are reliable, it design a path-constraint resource allocation algorithm to measure the reliability of relation paths and (2) represents relation paths via semantic composition of relation embeddings.

Abstract

Representation learning of knowledge bases aims to embed both entities and relations into a low-dimensional space. Most existing methods only consider direct relations in representation learning. We argue that multiple-step relation paths also contain rich inference patterns between entities, and propose a path-based representation learning model. This model considers relation paths as translations between entities for representation learning, and addresses two key challenges: (1) Since not all relation paths are reliable, we design a path-constraint resource allocation algorithm to measure the reliability of relation paths. (2) We represent relation paths via semantic composition of relation embeddings. Experimental results on real-world datasets show that, as compared with baselines, our model achieves significant and consistent improvements on knowledge base completion and relation extraction from text. The source code of this paper can be obtained from https://github.com/mrlyk423/ relation_extraction.

Authors

Zhiyuan Liu

34 papers

Yankai Lin

9 papers

Maosong Sun

46 papers

TL;DR

Abstract

Authors

References33 items

Learning Entity and Relation Embeddings for Knowledge Graph Completion

Knowledge Graph Embedding by Translating on Hyperplanes

Translating Embeddings for Modeling Multi-relational Data

Reasoning With Neural Tensor Networks for Knowledge Base Completion

Improving Learning and Inference in a Large Knowledge-Base using Latent Syntactic Cues

Connecting Language and Knowledge Bases with Embedding Models for Relation Extraction

Learning New Facts From Knowledge Bases With Neural Tensor Networks and Semantic Word Vectors

A semantic matching energy function for learning with multi-relational data

A latent factor model for highly multi-relational data

Reading The Web with Learned Syntactic-Semantic Inference Rules

Multi-instance Multi-label Learning for Relation Extraction

Semantic Compositionality through Recursive Matrix-Vector Spaces

Max-Margin Nonparametric Latent Feature Models for Link Prediction

Factorizing YAGO: scalable machine learning for linked data

Joint Learning of Words and Meaning Representations for Open-Text Semantic Parsing

Learning Structured Embeddings of Knowledge Bases

Random Walk Inference and Learning in A Large Scale Knowledge Base

A Three-Way Model for Collective Learning on Multi-Relational Data

Knowledge-Based Weak Supervision for Information Extraction of Overlapping Relations

Link Prediction in Complex Networks: A Survey

Relational retrieval using a combination of path-constrained random walks

Modeling Relations and Their Mentions without Labeled Text

Modelling Relational Data using Bayesian Clustered Tensor Factorization

Nonparametric Latent Feature Models for Link Prediction

Distant supervision for relation extraction without labeled data

Relational learning via collective matrix factorization

Freebase: a collaboratively created graph database for structuring human knowledge

Vector-based Models of Semantic Composition

Bipartite network projection and personal recommendation.

Fast Random Walk with Restart and Its Applications

Learning Systems of Concepts with an Infinite Relational Model

Compositional Vector Space Models for Knowledge Base Inference

Recurrent neural network based language model

Field of Study

Venue Information

Name

Type

URL

Alternate Names